hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from peft import PeftModel

tokenizer = AutoTokenizer.from_pretrained("hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling")
model = AutoModelForCausalLM.from_pretrained("BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf", torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {
      "role": "system",
      "content": (
        "You have access to the following tools:\n"
        "> Tool Name: get_current_weather\nTool Description: Get the current weather in a given location\n"
        "Tool Args:\n"
        "  - location (string, required): The city and state, e.g. San Francisco, CA\n"
        "  - unit (string): should be one of [\"celsius\", \"fahrenheit\"]\n\n"
        "Use the following format if using a tool:\n"
        "```\n"
        "Action: tool name (one of [get_current_weather]).\n"
        "Action Input: the input to the tool, in a JSON format representing the kwargs "
        "(e.g. ```{\"input\": \"hello world\", \"num_beams\": 5}```).\n"
        "```\n"
      )
    },
    {"role": "user", "content": "What is the weather like in Boston?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs, streamer=streamer)